Any broad idea on how much credits the GPU tasks could give ?

I have made some basic tests for GPU application...

At the moment, some functions are 30 times faster on my GPU (ATI 7770) then on CPU (E3-1230v2).
Unfortunately, we still have some problems with calculations precision and new problem with necessary temp file which uses about 4GB of HDD space for each work unit.

But...
Work is in progress :)

---

Krzysztof 'krzyszp' Piszczek

Member of Radioactive@Home team
My Patreon profile
Universe@Home on YT

Unfortunately, we still have some problems with calculations precision and new problem with necessary temp file which uses about 4GB of HDD space for each work unit.

I expect that the HDD space won't be a problem for many people, though it will be for some. Just give us a warning, and we can limit the WU's accordingly.

Unfortunately, we still have some problems with calculations precision and new problem with necessary temp file which uses about 4GB of HDD space for each work unit.

I expect that the HDD space won't be a problem for many people, though it will be for some. Just give us a warning, and we can limit the WU's accordingly.

I will do.
But I hope, we sort this out before public test starts...

---

Krzysztof 'krzyszp' Piszczek

Member of Radioactive@Home team
My Patreon profile
Universe@Home on YT

At the moment, some functions are 30 times faster on my GPU (ATI 7770) then on CPU (E3-1230v2).

Mmmm, i think what we can do with an AMD R9 Fury!!!

Work is in progress :)

:-)

Unfortunately, we still have some problems with calculations precision and new problem with necessary temp file which uses about 4GB of HDD space for each work unit.

The problem is not the space used by app, but the dimension of download from internet.

Unfortunately, we still have some problems with calculations precision and new problem with necessary temp file which uses about 4GB of HDD space for each work unit.

The problem is not the space used by app, but the dimension of download from internet.

No, this is temporary file.
Result files are small.

---

Krzysztof 'krzyszp' Piszczek

Member of Radioactive@Home team
My Patreon profile
Universe@Home on YT

I am developing an OpenCL application for AMD Radeon GPU's. I would like to write about progress and preliminary results of these works.
Firstly: this application is difficult and cumbersome case due to two problems: nonregular compulations (in the GPU scale where tens thousands jobs scheduled independently, regular jobs are very desired) and sophisticated code of main routines that will be ported to GPU world.
Secondly: I have some results that encouraged to further work. Routines of the main functions performed quite good on GPU (likes Radeon HD 7850). Main computations is doing on double precision, however timings on low-end and midrange GPU's are encouraged. The most routines ran 20-40x faster on GPU than on single core of CPU. I was testing code on my Core i5 (4GHz), and HD 7850 (1,01GHz). These results and timings need not to be reflecting final speedup of application. Workunits for GPU version can be many greater than CPU workunits for better scaling on GPU, and GPU application can need many more resources to run (mainly memory).
Unfortunatelly. I don't know when a GPU version will be finished and released to tests. Current state of the works doesn't allow to give any deadline.

Workunits for GPU version can be many greater than CPU workunits for better scaling on GPU, and GPU application can need many more resources to run (mainly memory)..

I use a ramdisk on some of my machines, and a write-cache on others, so I have to keep track of both working memory size and disk size. I have to provide 4GB of ramdisk space per work unit for the new CPDN WAH2 tasks, and about 3GB working memory for the ATLAS work units on CERN. And a lot of other people have do that too of course. It is a more than average, but not at all unprecedented. So do what you have to do, and good luck.

Thanks for the deep insight into the development!
So may need the time to develop in order to solve the problems.

Unfortunatelly. I don't know when a GPU version will be finished and released to tests. Current state of the works doesn't allow to give any deadline.

Nvidia 1080 is here and Amd Rx480 is coming.
No news since 2 months ago?

We are under preparing new app proces and the changes need to be ported to GPU as well...
At the current stage test GPU app I expect in about a month.

---

Krzysztof 'krzyszp' Piszczek

Member of Radioactive@Home team
My Patreon profile
Universe@Home on YT

We are under preparing new app proces and the changes need to be ported to GPU as well...
At the current stage test GPU app I expect in about a month.

Great!!
My little 260x is ready to taste your wus

I am still working over GPU app. I invented the engine that help to run massive number of tasks efficiently (including its irregularity) on GPU. First tests of this engine was passed correctly. Now, I am working over rewriting main code of the application to this engine. I can't write about speedup and majority of the possible potential bottlenecks. This engine will require a very little transfer between host and GPU and it will move the program control to GPU. I hope that engine allow to achieve good results under modern GPU (even if it will run quite complex code).

One month has passed away. Any new info?

One month has passed away. Any new info?

+1

I can write something about progress in development of GPU app. I wrote tentative version of CLRunEngine (engine that can help efficiently run complex code on GPU, including a sparse and non-regular control flow). Now, I writing an utility to facilitate porting complex from original app to CLRunEngine in enough natural way. Utility is not finished so far. Conversion from original code to code accepted by my engine would be a enough complex and cumbersome to maintain in handmade way. Therefore, I am trying to write an utility that help to move original to my engine.
Non-regular way of doing computations by original application and a sophisticated and sensitive code is enough big challenge for me. Very likely utility will be finished in next week or slightly later.

Non-regular way of doing computations by original application and a sophisticated and sensitive code is enough big challenge for me. Very likely utility will be finished in next week or slightly later.

Good job, boy!!!

Hi. Unfortunatelly, tool to generating code for engine has been postponed (likely, it will be finished later in this month). Just, I encountered few problems which were much difficult to solve. However, some progress has been reached in development of that tool. I have some plans to publish my tools (engine and generator) on open source license after porting the Universe@Home application to GPU.

Very great!
It takes the time it needs.